© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8458
    Prev
    Next
    INDEX
    Explanations

    Encryption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAT
    -0.27
    _cast
    -0.27
     temper
    -0.27
    çĸ®
    -0.26
     cast
    -0.26
     dub
    -0.26
    æĭĽ
    -0.26
    äºĶåĪĨéĴŁ
    -0.26
     minute
    -0.25
     casts
    -0.25
    POSITIVE LOGITS
    andon
    0.30
    rema
    0.27
    lias
    0.25
    ç¾ģ
    0.25
    otec
    0.25
    owment
    0.24
    ERVED
    0.24
     RuntimeObject
    0.24
    á»iji
    0.24
    èĩªæĿ¥æ°´
    0.23
    Activations Density 0.005%

    No Known Activations